← the index
makeplane/plane
6.9%
of 275 commits were committed by an AI agent — a floor, not an estimate
6.9% agent · top contributor 36.8%8 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

19
agent commits
256
human commits
8
agent contributors
36.8%
largest contributor

Assisted or autonomous

19assisted
0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. The agent ran git commit during a working session, with a person there. Autonomous — a bot identity is the author, no human in the loop. Across the whole index, 93.7% of agent commits are assisted.

Agent share by month

Feb26
Mar26
Apr26
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 16.2%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic134.7%
GitHub CopilotGitHub51.8%
Cursor AgentAnysphere10.4%

Verify it yourself

Sample commits that matched. Every one links to GitHub — check the trailers.

  • 3478d4fa[WEB-8352] fix(security): scope SubIssuesEndpoint to the URL project (#946Claude Code
  • 30527927[WEB-8103] fix: stop leaking webhook HMAC secret_key on reads (#9382)Claude Code
  • ddac107achore: remove Zenith managed hosting from README (#9693)Claude Code
  • af1be50b[WEB-8074] fix: scope IssueListEndpoint to guest created_by (#9374)GitHub Copilot
  • 4225bc59[GIT-175] fix: completed_at updation logic for work items (#9044)GitHub Copilot
  • da41f14achore(ci): suppress CodeQL file coverage deprecation warning (#8916)GitHub Copilot
  • 49c4da6dfix: strip control characters from sanitized filenames (#9151)Cursor Agent

What was excluded

Commits in window294
Merge commits removed4
CI / dependency bots removed15
Considered275

Bots are excluded from the denominator entirely. Counting dependabot as “AI-written code” is the fastest way to produce a meaningless number.

How this was measured

Measured over February–August 2026, cloned directly. Detection is deterministic string matching against signatures agents write about themselves — no heuristics, no style analysis. Merge commits and CI bots are excluded from the denominator. The figure is a floor: squash merges strip trailers, so real usage is higher. Contributor counts are aggregate — no individual is named.

Run it yourself: npx qmmit-cli makeplane/plane

Scan another repository